Description
Connect to your hosted MCP Server using any MCP client to communicate with tools
Agent Hygiene Score
Is this server safe to hand an autonomous AI agent? This score evaluates schema strictness, least-privilege scoping, declared boundaries, auditability, and maintenance — separate from our security audit.
🔬 Playground
Try Activepieces live in the browser with security context.
Installation
npx -y @activepieces/piece-mcpnpm install @activepieces/piece-mcpgit clone https://github.com/activepieces/activepiecesClaude Desktop Configuration
Add this configuration to your Claude Desktop config file to enable this MCP server:
Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json
Config file location: %APPDATA%\Claude\claude_desktop_config.json
Config file location: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"activepieces": {
"command": "npx",
"args": [
"-y",
"@activepieces/piece-mcp"
]
}
}
}Security Audit
| Dimension | Result | Details |
|---|---|---|
| Transport Security | Both | Stdio is local-only process communication. SSE/HTTP exposes network attack surface. |
| Authentication | API Key | Static API key — long-lived secret must be stored securely. |
| Token Lifecycle | Long-lived (Static) | Short-lived tokens limit exposure window if compromised. Long-lived tokens require secure rotation policies. |
| Input Handling | Parameterized (Safe) | Parameterized inputs prevent injection attacks. Shell strings enable command injection vectors. |
| Data Residency | Cloud | Local-only data never leaves your machine. Cloud residency means data flows through third-party APIs. |
Community Reviews
Authenticated reviews from GitHub users. No anonymous submissions. Your experience helps others choose wisely.
No reviews yet. Be the first to share your experience.